C

Cycode Cli

Cycode CLI is a locally installed application used to scan code repositories for security vulnerabilities, including sensitive information leakage, Infrastructure as Code misconfigurations, Software Composition Analysis vulnerabilities, and Static Application Security Testing issues. This tool supports multiple scan types, such as repository scanning, path scanning, and commit history scanning, and provides an ignore rule function to exclude specific results.
3 points
2

What is the Model Context Protocol (MCP) Server?

The MCP server is a protocol service for AI systems to interact with Cycode's scanning tools. It allows AI models to access Cycode's scanning functions, such as secret scanning, SCA scanning, IaC scanning, and SAST scanning, through a standardized protocol.

How to Use the MCP Server?

The MCP server can be started via the command line and configured with different transmission methods (e.g., stdio, SSE, streamable-http). Users can integrate the MCP server into various AI tools, such as VS Code, GitHub Copilot, Cursor, and Claude Desktop.

Use Cases

The MCP server is suitable for scenarios where code security scanning functions need to be embedded in AI tools. For example, developers can get real-time security suggestions while writing code, or security checks can be automatically performed in the CI/CD process.

Main Features

Multi-platform SupportSupports multiple transmission methods, including stdio, SSE, and streamable-http, suitable for different AI tools and environments.
AI IntegrationAllows AI models to call Cycode's scanning functions through a standardized protocol, enabling intelligent security checks.
Flexible ConfigurationProvides rich configuration options, such as specifying the host address, port, and transmission type, to meet different needs.
Global InstallationIt is recommended to install Cycode CLI globally to seamlessly integrate the MCP server into all projects.

Advantages and Limitations

Advantages
Supports multiple transmission methods to meet the needs of different AI tools.
Provides clear configuration options for users to customize settings easily.
Easy to integrate into mainstream development tools to improve development efficiency.
Supports real-time AI feedback to enhance code security.
Limitations
Requires a certain technical foundation to configure and run the MCP server.
Some advanced features may require additional permissions or configuration.
Incompatible with older versions of Python. Make sure the environment meets the requirements.
Some functions rely on external services, and network connectivity may affect performance.

How to Use

Install Cycode CLI
First, install Cycode CLI. It is recommended to use pip or brew for installation.
Authenticate Cycode CLI
Use the `cycode auth` command to log in to the Cycode platform and complete identity verification.
Start the MCP Server
Run the `cycode mcp` command to start the MCP server, using stdio transmission by default.
Configure the MCP Server
Select the transmission method according to your needs, such as SSE or streamable-http, and specify the host and port.

Usage Examples

Integrate the MCP Server with VS CodeConfigure the MCP server in VS Code so that the AI assistant can provide real-time code security suggestions.
Integrate with GitHub CopilotIntegrate the MCP server with GitHub Copilot to help developers discover security issues immediately while writing code.
Integrate with Cursor IDEUse the MCP server in Cursor IDE to provide users with a more intelligent code review experience.

Frequently Asked Questions

What dependencies does the MCP server require?
How to solve the problem of the MCP server failing to start?
What transmission methods does the MCP server support?
How to use the MCP server in the CI/CD process?

Related Resources

MCP Protocol Specification
The official documentation of the MCP protocol, detailing the transmission methods and protocol details.
Cycode CLI Official Documentation
The complete documentation of Cycode CLI, including installation, configuration, and usage instructions.
MCP Server Configuration Example
The Cycode CLI repository on GitHub, containing configuration examples and usage methods for the MCP server.
Cycode CLI Installation Guide
The installation tutorial for Cycode CLI, covering the installation steps for different operating systems.
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "cycode": {
      "command": "cycode",
      "args": ["mcp"],
      "env": {
        "CYCODE_CLIENT_ID": "your-cycode-id",
        "CYCODE_CLIENT_SECRET": "your-cycode-secret-key",
        "CYCODE_API_URL": "https://api.cycode.com",
        "CYCODE_APP_URL": "https://app.cycode.com"
      }
    }
  }
}

{
  "mcpServers": {
    "cycode": {
      "command": "pipx",
      "args": ["run", "cycode", "mcp"],
      "env": {
        "CYCODE_CLIENT_ID": "your-cycode-id",
        "CYCODE_CLIENT_SECRET": "your-cycode-secret-key",
        "CYCODE_API_URL": "https://api.cycode.com",
        "CYCODE_APP_URL": "https://app.cycode.com"
      }
    }
  }
}

{
  "mcpServers": {
    "cycode": {
      "command": "uvx",
      "args": ["cycode", "mcp"],
      "env": {
        "CYCODE_CLIENT_ID": "your-cycode-id",
        "CYCODE_CLIENT_SECRET": "your-cycode-secret-key",
        "CYCODE_API_URL": "https://api.cycode.com",
        "CYCODE_APP_URL": "https://app.cycode.com"
      }
    }
  }
}

{
  "mcpServers": {
    "cycode": {
      "url": "http://127.0.0.1:8000/sse"
    }
  }
}

{
  "mcpServers": {
    "cycode": {
      "url": "http://127.0.0.1:8080/sse"
    }
  }
}

{
  "mcpServers": {
    "cycode": {
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Z
Zen MCP Server
Zen MCP is a multi-model AI collaborative development server that provides enhanced workflow tools and cross-model context management for AI coding assistants such as Claude and Gemini CLI. It supports seamless collaboration of multiple AI models to complete development tasks such as code review, debugging, and refactoring, and can maintain the continuation of conversation context between different workflows.
Python
15
5 points
C
Container Use
Container Use is an open-source tool that provides a containerized isolated environment for coding agents, supporting parallel development of multiple agents without interference.
Go
10
5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
374
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
888
4.3 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
359
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
146
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
658
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
583
5 points
Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
150
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
199
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
888
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
612
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
332
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
795
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase